torch_geometric.datasets.SHREC2016

class SHREC2016(root: str, partiality: str, category: str, train: bool = True, transform: Optional[Callable] = None, pre_transform: Optional[Callable] = None, pre_filter: Optional[Callable] = None, force_reload: bool = False)[source]

Bases: InMemoryDataset

The SHREC 2016 partial matching dataset from the “SHREC’16: Partial Matching of Deformable Shapes” paper. The reference shape can be referenced via dataset.ref.

Note

Data objects hold mesh faces instead of edge indices. To convert the mesh to a graph, use the torch_geometric.transforms.FaceToEdge as pre_transform. To convert the mesh to a point cloud, use the torch_geometric.transforms.SamplePoints as transform to sample a fixed number of points on the mesh faces according to their face area.

Parameters:

  • root (str) – Root directory where the dataset should be saved.

  • partiality (str) – The partiality of the dataset (one of "Holes", "Cuts").

  • category (str) – The category of the dataset (one of "Cat", "Centaur", "David", "Dog", "Horse", "Michael", "Victoria", "Wolf").

  • train (bool, optional) – If True, loads the training dataset, otherwise the test dataset. (default: True)

  • transform (callable, optional) – A function/transform that takes in an torch_geometric.data.Data object and returns a transformed version. The data object will be transformed before every access. (default: None)

  • pre_transform (callable, optional) – A function/transform that takes in an torch_geometric.data.Data object and returns a transformed version. The data object will be transformed before being saved to disk. (default: None)

  • pre_filter (callable, optional) – A function that takes in an torch_geometric.data.Data object and returns a boolean value, indicating whether the data object should be included in the final dataset. (default: None)

  • force_reload (bool, optional) – Whether to re-process the dataset. (default: False)